© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108586
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦå½¢å¼ı
    -0.29
    oton
    -0.29
    ä¸Ĭè¯ī
    -0.28
    æķħ
    -0.27
    bia
    -0.26
    ised
    -0.25
     releg
    -0.25
    arin
    -0.24
    人å±ħ
    -0.24
    ething
    -0.24
    POSITIVE LOGITS
    åIJįå½ķ
    0.29
    notations
    0.29
    管çIJĨç³»ç»Ł
    0.28
    clusions
    0.28
    ability
    0.28
    urations
    0.27
    姿åĬ¿
    0.27
     makeover
    0.27
    rians
    0.27
     questionnaire
    0.27
    Activations Density 2.358%

    No Known Activations